https://github.com/treytuscai/transformers

Implements a GPT‑style Transformer architecture from Vaswani et al. (2017) to generate text and solve arithmetic tasks.
https://github.com/treytuscai/transformers

nlp python tensorflow transformer

Last synced: 3 months ago
JSON representation

Implements a GPT‑style Transformer architecture from Vaswani et al. (2017) to generate text and solve arithmetic tasks.

• Host: GitHub
• URL: https://github.com/treytuscai/transformers
• Owner: treytuscai
• Created: 2025-04-19T17:47:41.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-05-15T00:23:37.000Z (about 1 year ago)
• Last Synced: 2025-05-25T16:49:38.053Z (about 1 year ago)
• Topics: nlp, python, tensorflow, transformer
• Language: Jupyter Notebook
• Homepage:
• Size: 1.8 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 🔁 Transformers

Implements a GPT-style Transformer model from scratch using our modular deep learning library, [![DeepNeuralLib](https://img.shields.io/badge/Repo-DeepNeuralLib-blue?logo=github)](https://github.com/treytuscai/DeepNeuralLib). Trains small transformers to perform arithmetic tasks and larger ones to generate Shakespearean text, showcasing attention mechanisms and positional encoding.